Konsultan arsitektur perusahaan: KPK, RistekDikti, INSW, BPPT, Kementerian Sosial Kementerian Keuangan (Itjend, DJBC, DJPK), Telkom, FIF, PLN, PJB, Pertamina EP, dll. Saluran Youtube: Romi Satria Wahono). Referensi dan pedoman penting bagi peneliti yang baru memulai penelitiannya agar dapat memahami topik/tema penelitian secara menyeluruh.
Traditional Review
Systematic Mapping Study (Scoping Study) 3. Systematic Literature Review or Systematic
Tertiary Study (SLR of SLR)
Galar et al., An Ensemble Review for the Class Imbalance Problem: Bagging, Boosting, and Hybrid Approaches, IEEE Transactions on Systems, Humans, and Cybernetics, Part C (Applications and Reviews), vol.
Systematic Mapping Study
The purpose of a systematic literature review is to provide as complete a list as possible of all. published studies relating to a particular subject area. A process of identifying, evaluating and interpreting all available research evidence to provide answers to a specific research question. Kitchenham & Charters, Guidelines for Conducting a Systematic Literature Review in Software Technology, EBSE Technical Report version.
Systematic Literature Review (SLR)
Kitchenham & Charters, Guidelines in Performing Systematic Literature Reviews in Software Engineering, EBSE Technical Report version 2.3, 2007). Romi Satria Wahono, A Systematic Literature Review of Software Defect Prediction: Research Trends, Data Sets, Methods, and Frameworks, Journal of Software. Matthias Galster, Danny Weyns, Dan Tofan, Bartosz Michalik, and Paris Avgeriou, Variability in Software Systems: A Systematic Literature Review, IEEE.
Tertiary study
Untuk mempercepat
Lanjutkan penentuan topik
Penentuan Topik Penelitian
Cari Tertiery Study di Bidang Software Engineering
Setelah kita paham beberapa topik penelitian di bidang software engineering dari Tertiery Study
Langkah berikutnya, kita kumpulkan seluruh SLR dengan keyword topik seperti di paper Tertiery
Lanjutkan dengan mengejar seluruh SLR dari
Cari SLR dari Topik Penelitian yang Dipilih
Rekayasa perangkat lunak global Metode dan teknik untuk mengembangkan dan melayani perangkat lunak dengan lingkungan dan sumber daya yang tersebar di banyak negara. Metode dan teknik Rekayasa Persyaratan untuk mengumpulkan persyaratan dalam proses pengembangan Perangkat Lunak Sistem Adaptif Mandiri dengan sifat otonom dan penyembuhan diri. Arsitektur perangkat lunak Metode dan teknik untuk mengembangkan arsitektur perangkat lunak untuk mengurangi kompleksitas: arsitektur model-view-controller, arsitektur perusahaan, dll.
Arsitektur Berorientasi Layanan Metode dan teknik pengembangan dan pelayanan perangkat lunak sebagai layanan (Software as a Service (SaaS)) dan proses penyampaiannya kepada pengguna Konstruksi Perangkat Lunak Metode dan teknik konstruksi perangkat lunak, meliputi: paradigma pemrograman, pemrograman kode, refactoring, clone deteksi, konvensi kode, dll. Pengalihdayaan perangkat lunak Metode dan teknik pengalihdayaan dan pengalihdayaan pengembangan dan layanan perangkat lunak, termasuk: strategi dan parameter dalam pemilihan vendor, dll.
Lini Produk Perangkat Lunak Metode dan teknik untuk mengembangkan dan mengklasifikasikan produk perangkat lunak yang mempunyai sifat dan tujuan yang sama. Pengujian Perangkat Lunak Metode dan teknik pengujian perangkat lunak untuk berbagai jenis pengujian dan platform Penelitian Tinjauan Literatur Sistematis yang membahas satu topik penelitian dalam rekayasa perangkat lunak.
Identify the relevant literature
Perform selection of primary studies 3. Perform data extraction
Assess studies’ quality
Conduct synthesis of evidence
Write up the SLR report/paper 2. Choose the Right Journal
Introduction
Main Body
Review method – briefly describe steps taken to conduct the review
Results – findings from the review
Discussion – implication of review for research & practice
Conclusions
Romi Satria Wahono, A Systematic Literature Review of Software Defect Prediction: Research Trends, Dataset, Methods and Frameworks, Journal of Software Engineering, Vol. Intervention Software defect prediction, failure prediction, failure prone, detection, classification, estimation, models, methods, techniques, datasets.
PICOC
Estimating the number of defects remaining in software systems using estimation algorithm
Discovering defect associations using association rule algorithm (Association)
Classifying the defect-proneness of software
Clustering the software defect based on object using clustering algorithm (Clustering)
Analyzing and pre-processing the software defect datasets (Dataset Analysis)
International Conference on Natural Computing IEEE Transactions on Knowledge and Data Engineering IEEE Transactions on Systems, People and Cybernetics IEEE Transactions on Reliability. LOC_code_and_comment NCSLOC The number of lines containing both code and comment in a module. The accurate and reliable classification algorithms to build a better prediction model is an outstanding problem in software error prediction.
Menzies Framework
Lessmann Framework
Song
The comparisons and benchmarking result of the defect prediction using machine learning classifiers indicate
Noisy attribute predictors and imbalanced class distribution of software defect datasets result in
Neural network and support vector machine have strong fault tolerance and strong ability of nonlinear
Noisy feature predictors and unbalanced class distribution of software defect datasets lead to inaccuracy of classification models. Neural network has a strong fault tolerance and a strong capability of nonlinear dynamic processing of software fault data, but feasibility of. Romi Satria Wahono, Nanna Suryana Herman and Sabrina Ahmad, A Comparison Framework of Classification Models for Software Defect Prediction , Advanced Science Letters, Vol.
Romi Satria Wahono and Nanna Suryana Herman, Genetic Feature Selection for Software Defect Prediction, Advanced Science Letters, Vol. Romi Satria Wahono and Nanna Suryana, A Combination of Particle Swarm Optimization-Based Feature Selection and Baggage Technique for Software Defect Prediction. Romi Satria Wahono, Nanna Suryana and Sabrina Ahmad, Metaheuristic, Neural Network Parameter Optimization Based on Genetic Algorithm for Software.
Romi Satria Wahono, Nanna Suryana, and Sabrina Ahmad, Metaheuristic Optimization Based Feature Selection for Software Defect Prediction, Journal of. There are noisy data points in the software defect data sets that cannot be confidently assumed to be false using such a simple method (Gray, Bowes, Davey, & Christianson, 2011). Software failure prediction performance improved when irrelevant and redundant attributes were removed (Wang, Khoshgoftaar, & Napolitano, 2010).
The software defect prediction performance decreases significantly because the data set contains noisy characteristics (Kim, . Zhang, Wu, & Gong, 2011). Software defect datasets have an unbalanced nature with very few defective modules compared to defect-free ones (Tosun, Bener, Turhan, & Menzies, 2010). Imbalance can lead to a model that is not practical in software defect prediction because most cases will be predicted as non-defect prone (Khoshgoftaar, Van Hulse, & Napolitano, 2011).
How does the integration between genetic algorithm-based feature selection and baggage technique affect the accuracy of software defect prediction. To develop a hybrid particle swarm optimization-based feature selection and baggage technique for improving the accuracy of software defect prediction. Which metaheuristic optimization techniques perform best when used in feature selection of software defect prediction.
Dari research gaps yang ditemukan ketika
Bagian kedua proposal adalah SLR yang sudah kita susun
Tujuan Semester 1 program Ph.D adalah untuk meningkatkan SLR sehingga dapat menjadi makalah yang layak untuk diajukan ke jurnal. Dan dosen pembimbing perlu yakin bahwa kami bisa bergerak cepat karena segala sesuatunya sudah kami persiapkan sebelum masuk program S3. Aktiflah di kelas, tunjukkan bahwa kita datang ke kelas dengan “kepala penuh isi”, bukan kepala kosong yang siap disuapi apa pun oleh dosen.
Research is a considered activity, the goal of which is to make an original contribution to knowledge. contribution to the body of knowledge in the research area of interest).
Memperbaiki C4.5
Memperbaiki Use Case Points
Memperbaiki Genetic Algorithms
20, Romi Satria Wahono, Nanna Suryana and Sabrina Ahmad, Metaheuristic optimization based feature selection for software defect prediction, Journal of.
A Comparison Framework of Classification Models for
Software Defect Prediction (CF SDP)
- Romi Satria Wahono, Nanna Suryana Herman and Sabrina Ahmad, A Comparison Framework of Classification
- Romi Satria Wahono, Nanna Suryana Herman and Sabrina Ahmad, A Comparison Framework of Classification
If the P-value is < 0.05 (bold), it indicates that there is a significant difference between two classifiers. Based on the significant difference results, there is no significant difference between the LR, NB, BP, and SVM models. Romi Satria Wahono, Nanna Suryana Herman and Sabrina Ahmad, A Comparison Framework for Classification Ahmad, A Comparison Framework for Classification.
SCOPUS SJR: 0.240)
A Hybrid Genetic Algorithm based Feature Selection
Romi Satria Wahono and Nanna Suryana Herman, Genetic Feature Selection for Software Defect Prediction,
Romi Satria Wahono and Nanna Suryana Herman, Genetic Feature Selection for Software Defect Prediction,
A Hybrid Particle Swarm
Optimization based Feature Selection and Bagging
Technique for Software
Defect Prediction (PSOFS+B)
Although there are two classifiers that have no significant difference (P > 0.05), the results showed that those of the remaining eight classifiers have a significant difference (P < 0.05). Romi Satria Wahono and Nanna Suryana, Combining Particle Swarm Optimization Feature Selection and Bagging Technique for Software Defect Prediction, International Journal of Software Engineering and Its Applications, Vol 7, no. 5, September 2013. Although there are two classifiers that are significantly different (P < NB and SVM), the results showed that the remaining eight classifiers have no significant difference (P > 0.05).
There is no significant difference between PSO and GA when used as feature selection for most classifiers. Romi Satria Wahono, Nanna Suryana and Sabrina Ahmad, Metaheuristic Optimization based Feature Selection for Software Defect Prediction, Journal of Software, Vol.
SCOPUS SJR: 0.260)
Perbaikan dari Proposal dan Perubahan Hasil Penelitian
Systematic Literature Review (SLR)
RC3: PSOFS+B)
RC5: NNGAPO+B)Paper 2
RC2: GAFS+B)Paper 1
RC1: CF-SDP)
5 KIAT S3
Lulus Tepat Waktu